A New Fault Diagnosis of Multifunctional Spoiler System Using Integrated Artificial Neural Network and Discrete Wavelet Transform Methods

Abstract

Multifunctional spoiler (MFS) is one of the most critical parts of the jet aircraft that can be degraded due to incipient faults and consequently jeopardize the safety of a flight. This paper introduces a new fault diagnosis method for the MFS using fusion methodology. Three main faults, including null bias current, actuator leakage coefficient, and internal leakage faults are considered and three parallel fusion blocks are invoked to isolate these faults in the system. In each block, an integrated method using an artificial neural network (ANN) and discrete wavelet transform (DWT) is developed via ordered weighted averaging operator to achieve a higher reliability and faster diagnosing system. Moreover, several test scenarios are examined to validate the system performance under faulty conditions. Simulation results show the capability of the system in isolating incipient faults in comparison with ANN and DWT methods.